Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provoke
    -0.07
    jur
    -0.06
    .throw
    -0.06
     Orlando
    -0.06
     grind
    -0.06
     praž
    -0.06
    _GRID
    -0.06
    CREASE
    -0.06
    clave
    -0.06
     Forced
    -0.06
    POSITIVE LOGITS
     run
    0.07
    /ss
    0.06
     αρ
    0.06
    su
    0.06
    Si
    0.06
    /welcome
    0.06
    :i
    0.06
    ((-
    0.06
    �
    0.06
     running
    0.06
    Act Density 0.032%

    No Known Activations